A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
A faster graph kernel using optical random features.
A new method improves graph random features with quasi-Monte Carlo techniques.
Adding node feature kernels improves GCN robustness to graph perturbations.
Graph neural networks (GNNs) are powerful machine learning models for various graph learning tasks. Recently, the limitations of the expressive power of various GNN models have been revealed. For example, GNNs cannot distinguish some non-isomorphic graphs and they cannot learn efficient graph algorithms. In this paper,…
Enhances graph neural networks with random walks to improve performance.
Graph matching with feature vectors is solved using a two-layer graph neural network.
Graph kernels are widely used for measuring the similarity between graphs. Many existing graph kernels, which focus on local patterns within graphs rather than their global properties, suffer from significant structure information loss when representing graphs. Some recent global graph kernels, which utilizes the align…
Random weights in GNNs match learned weights in performance.
GraphMoE generates random graphs using neural networks and graphlets.
A novel algorithm for unbiased graph kernel estimation with subquadratic time complexity.
GNNs with random node initialization are shown to be universally expressive.
A new method for graph-structured data improves transformer performance by incorporating topology.
Graph neural networks improve with affinity measures from random walks.
We present Graph Random Neural Features (GRNF), a novel embedding method from graph-structured data to real vectors based on a family of graph neural networks. The embedding naturally deals with graph isomorphism and preserves the metric structure of the graph domain, in probability. In addition to being an explicit em…
Graph Neural Networks struggle on random graphs without node identifiers.
Proposes a new method to describe graph vertex features using characteristic functions.
SASE improves attributed graph clustering for large graphs with linear time and space complexity.
Graphs (networks) are ubiquitous and allow us to model entities (nodes) and the dependencies (edges) between them. Learning a useful feature representation from graph data lies at the heart and success of many machine learning tasks such as classification, anomaly detection, link prediction, among many others. Many exi…
Feature extraction and dimension reduction for networks is critical in a wide variety of domains. Efficiently and accurately learning features for multiple graphs has important applications in statistical inference on graphs. We propose a method to jointly embed multiple undirected graphs. Given a set of graphs, the jo…
We show that the classification performance of graph convolutional networks (GCNs) is related to the alignment between features, graph, and ground truth, which we quantify using a subspace alignment measure (SAM) corresponding to the Frobenius norm of the matrix of pairwise chordal distances between three subspaces ass…
We propose a novel model for generating graphs similar to a given example graph. Unlike standard approaches that compute features of graphs in Euclidean space, our approach obtains features on a surface of a hypersphere. We then utilize a von Mises-Fisher distribution, an exponential family distribution on the surface …
Generative model controls heterophily in graph signals.
DiAL uses Bayesian Dirichlet random fields for active learning with sparse labels.
GTDL methods fail to accurately model feature interactions in tabular data.
ParPIC clusters directed graphs using random walks and diffusion operators.
It is not until recently that graph neural networks (GNNs) are adopted to perform graph representation learning, among which, those based on the aggregation of features within the neighborhood of a node achieved great success. However, despite such achievements, GNNs illustrate defects in identifying some common struct…
A new graph neural network tackles oversmoothing and generalization issues.
Modern data analysis pipelines are becoming increasingly complex due to the presence of multi-view information sources. While graphs are effective in modeling complex relationships, in many scenarios a single graph is rarely sufficient to succinctly represent all interactions, and hence multi-layered graphs have become…
Random walks are at the heart of many existing deep learning algorithms for graph data. However, such algorithms have many limitations that arise from the use of random walks, e.g., the features resulting from these methods are unable to transfer to new nodes and graphs as they are tied to node identity. In this work, …
Spectral clustering is one of the most effective clustering approaches that capture hidden cluster structures in the data. However, it does not scale well to large-scale problems due to its quadratic complexity in constructing similarity graphs and computing subsequent eigendecomposition. Although a number of methods h…
Random walks are at the heart of many existing network embedding methods. However, such algorithms have many limitations that arise from the use of random walks, e.g., the features resulting from these methods are unable to transfer to new nodes and graphs as they are tied to vertex identity. In this work, we introduce…
This paper explores GNN functions on random graphs, highlighting the importance of node Positional Encodings.
GCNs help in diagnosing label scarcity and feature quality on graphs.
GAT-RWOS uses graph attention to improve imbalanced data classification.
Spectral clustering has become a popular technique due to its high performance in many contexts. It comprises three main steps: create a similarity graph between N objects to cluster, compute the first k eigenvectors of its Laplacian matrix to define a feature vector for each object, and run k-means on these features t…
Graph convolutional neural networks (GCNN) have been successfully applied to many different graph based learning tasks including node and graph classification, matrix completion, and learning of node embeddings. Despite their impressive performance, the techniques have a limited capability to incorporate the uncertaint…
New framework models epistemic uncertainty in GNNs using random sets.
EPFGNN models graph connections for better node classification.
New methods learn from single graphs, improving transductive node classification.
This paper proposes a method to select relevant features for multi-label learning.
Unified model combines feature and label propagation for semi-supervised classification.
Deep learning models have achieved huge success in numerous fields, such as computer vision and natural language processing. However, unlike such fields, it is hard to apply traditional deep learning models on the graph data due to the 'node-orderless' property. Normally, adjacency matrices will cast an artificial and …
Non-linear kernel methods can be approximated by fast linear ones using suitable explicit feature maps allowing their application to large scale problems. We investigate how convolution kernels for structured data are composed from base kernels and construct corresponding feature maps. On this basis we propose exact an…
Random features are improved by variance-reducing couplings, enhancing machine learning models.
A scalable GP model for online uncertainty quantification over graphs.
A parametrization of hypergraphs based on the geometry of points in is developed. Informative prior distributions on hypergraphs are induced through this parametrization by priors on point configurations via spatial processes. This prior specification is used to infer conditional independence models or M…
ARGEW improves node embeddings for weighted homophilous graphs by emphasizing strong edge weights.
Stochastic Kronecker graphs supply a parsimonious model for large sparse real world graphs. They can specify the distribution of a large random graph using only three or four parameters. Those parameters have however proved difficult to choose in specific applications. This article looks at method of moments estimators…